Mapping Advertiser Intents to Keywords

• US 20120059708A1
• Filed: 08/26/2011
• Published: 03/08/2012
• Est. Priority Date: 08/27/2010
• Status: Abandoned Application

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Adchemy Incorporated (WalMart Inc.)
• Inventors: Galas, Daniel, Thumasathit, Veeravich Thi, Nukala, Murthy V., Chatwin, Richard Edward, Magnani, Alessandro, Foster, Benjamin David, Coleman, Alan, Khettry, Manish, Chandrasekar, Siva, Gupta, Nitin, Kondaji, Srinidhi Ramesh
• Application Number:
  US13/219,455
• Publication Number:
  US 20120059708A1
• Time in Patent Office: Days
• US Class Current: 705/14.43
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0244 Optimization
• CPC Class Codes: G06Q 30/0247 Calculate past, present or future revenues
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0276 Advertisement creation

Abstract

In one embodiment, a method includes constructing an intent map for a plurality of products, the intent map comprising intent topics and each intent topic comprising intents, and then deriving a plurality of keywords from the intent map based on keyword templates.

Claims

1. A method comprising:

by one or more computing devices,

constructing an intent map for a plurality of products, wherein;

the intent map comprises one or more intent topics, and

each of the one or more intent topics comprises one or more intents; and

deriving a plurality of keywords from the intent map based on one or more keyword templates.

2. The method of claim 1, further comprising constructing the one or more keyword templates.

3. The method of claim 2, wherein at least one of the one or more keyword templates is constructed based on one or more rules.

4. The method of claim 3, wherein the one or more rules are determined based on the one or more intent topics.

5. The method of claim 2, wherein:

the one or more intent topics form a hierarchy; and

at least one of the one or more keyword templates is constructed based on the hierarchy.

6. The method of claim 2, wherein at least one of the one or more keyword templates is constructed based on a collection of known keywords, comprising:

analyzing the collection of known keywords;

selecting, from the collection of known keywords, one or more known keywords that are applicable to the intent map; and

constructing the at least one of the one or more keyword templates based on the one or more known keywords.

7. The method of claim 6, wherein selecting, from the collection of known keywords, the one or more known keywords that are applicable to the intent map comprises:

selecting, from the collection of known keywords, one or more specific known keywords that are related to the plurality of products;

analyzing historical performance information of the one or more specific known keywords that are related to the plurality of products; and

selecting, from the one or more specific known keywords that are related to the plurality of products, the one or more known keywords that have relatively higher performance with respect to one or more predetermined metrics.

8. The method of claim 6, wherein constructing the one or more keyword templates based on the one or more known keywords comprises:

for each of the one or more known keywords,

dividing the known keyword into one or more segments; and

for each of at least one of the one or more segments,

identifying an intent from the intent map that aligns with the segment; and

replacing the segment with an intent topic from the intent map to which the intent belongs.

9. The method of claim 1, wherein at least one of the one or more keyword templates comprises at least one intent topic from the intent map.

10. The method of claim 9, wherein deriving the plurality of keywords from the intent map based on the one or more keyword templates comprises:

deriving one or more of the plurality of keywords based on each of the one or more keyword templates;

wherein;

the one or more intent topics form a hierarchy; and

deriving one of the plurality of keywords based on one of the one or more keyword templates comprises replacing each of the at least one intent topic contained in the one keyword template with an intent from the intent topic or from an intent topic that is an ancestor of the intent topic in the hierarchy.

11. The method of claim 1, further comprising filtering the plurality of keywords, comprising:

estimating a marketing or advertising volume for the plurality of keywords; and

selecting, from the plurality of keywords, one or more keywords that are estimated to generate a relatively higher marketing or advertising volume.

12. The method of claim 1, further comprising clustering the plurality of keywords into one or more keyword clusters.

13. The method of claim 12, wherein clustering the plurality of keywords into the one or more keyword clusters comprises:

specifying a set of intent topics along which to cluster, wherein the set of intent topics comprises at least one of the one or more intent topics; and

grouping the plurality of keywords based on the set of intent topics, comprising;

grouping all keywords that, for each intent topic in the set of intent topics commonly share a same intent from that intent topic, into a keyword cluster.

14. The method of claim 12, further comprising constructing one or more advertisements for each of the one or more keyword clusters.

15. The method of claim 1, wherein each of the one or more intent topics of the intent map relates to one or more intent-topic categories.

16. The method of claim 15, wherein the one or more intent-topic categories comprise one or more of product categories, products, general product descriptions, specific product descriptions, calls to action, or call-to-action descriptions.

17. The method of claim 1, wherein the one or more intent topics form one or more hierarchies.

18. The method of claim 17, wherein each of the one or more hierarchies comprises:

a set of intent topics, comprising at least one of the one or more intent topics; and

a plurality of levels, each comprising at least one intent topic from the set of intent topics.

19. The method of claim 18, wherein:

each of the one or more intent topics belongs to one of a plurality of intent-topic categories; and

for each of the one or more hierarchies, each intent topic from the set of intent topics belongs to a common intent-topic category.

20. The method of claim 1, wherein there are one or more topic relationships among the one or more intent topics and one or more intent relationships among the one or more intents of the one or more intent topics.

21. The method of claim 20, wherein one of the one or more topic relationships between a first intent topic and a second intent topic indicates that a first intent belonging to the first intent topic and a second intent belonging to the second intent topic are either eligible or not eligible to appear together in at least one of the plurality of keywords.

22. The method of claim 20, wherein one of the one or more intent relationships between a first intent belonging to a first intent topic and a second intent belonging to a second intent topic indicates that the first intent and the second intent are eligible to appear together in at least one of the plurality of keywords.

23. The method of claim 20, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a synonym of the second intent.

24. The method of claim 20, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a plural form of the second intent.

25. The method of claim 20, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a misspelling of the second intent.

26. The method of claim 20, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent and the second intent are eligible to be substitutes for each other in at least one of the plurality of keywords.

27. The method of claim 1, wherein the plurality of products belongs to a same business or industry.

28. The method of claim 1, where a product is a physical product, a software product, or a service.

29. A system comprising:

a memory comprising instructions executable by one or more processors; and

the one or more processors coupled to the memory and operable to execute the instructions, the one or more processors being operable when executing the instructions to;

construct an intent map for a plurality of products, wherein;

the intent map comprises one or more intent topics, and

each of the one or more intent topics comprises one or more intents; and

derive a plurality of keywords from the intent map based on one or more keyword templates.

30. The system of claim 29, wherein the one or more processors are further operable when executing the instructions to construct the one or more keyword templates.

31. The system of claim 30, wherein at least one of the one or more keyword templates is constructed based on one or more rules.

32. The system of claim 31, wherein the one or more rules are determined based on the one or more intent topics.

33. The system of claim 30, wherein:

the one or more intent topics form a hierarchy; and

at least one of the one or more keyword templates is constructed based on the hierarchy.

34. The system of claim 30, wherein at least one of the one or more keyword templates is constructed based on a collection of known keywords, comprising:

analyze the collection of known keywords;

select, from the collection of known keywords, one or more known keywords that are applicable to the intent map; and

construct the at least one of the one or more keyword templates based on the one or more known keywords.

35. The system of claim 34, wherein selecting, from the collection of known keywords, the one or more known keywords that are applicable to the intent map comprises:

select, from the collection of known keywords, one or more specific known keywords that are related to the plurality of products;

analyze historical performance information of the one or more specific known keywords that are related to the plurality of products; and

select, from the one or more specific known keywords that are related to the plurality of products, the one or more known keywords that have relatively higher performance with respect to one or more predetermined metrics.

36. The system of claim 34, wherein constructing the one or more keyword templates based on the one or more known keywords comprises:

for each of the one or more known keywords,

divide the known keyword into one or more segments; and

for each of at least one of the one or more segments,

identify an intent from the intent map that aligns with the segment; and

replace the segment with an intent topic from the intent map to which the intent belongs.

37. The system of claim 29, wherein at least one of the one or more keyword templates comprises at least one intent topic from the intent map.

38. The system of claim 37, wherein deriving the plurality of keywords from the intent map based on the one or more keyword templates comprises:

derive one or more of the plurality of keywords based on each of the one or more keyword templates;

wherein;

the one or more intent topics form a hierarchy; and

deriving one of the plurality of keywords based on one of the one or more keyword templates comprises replace each of the at least one intent topic contained in the one keyword template with an intent from the intent topic or from an intent topic that is an ancestor of the intent topic in the hierarchy.

39. The system of claim 29, wherein the one or more processors are further operable when executing the instructions to filter the plurality of keywords, comprising:

estimate a marketing or advertising volume for the plurality of keywords; and

select, from the plurality of keywords, one or more keywords that are estimated to generate a relatively higher marketing or advertising volume.

40. The system of claim 29, wherein the one or more processors are further operable when executing the instructions to cluster the plurality of keywords into one or more keyword clusters.

41. The system of claim 40, wherein clustering the plurality of keywords into the one or more keyword clusters comprises:

specify a set of intent topics along which to cluster, wherein the set of intent topics comprises at least one of the one or more intent topics; and

group the plurality of keywords based on the set of intent topics, comprising;

group all keywords that, for each intent topic in the set of intent topics commonly share a same intent from that intent topic, into a keyword cluster.

42. The system of claim 40, wherein the one or more processors are further operable when executing the instructions to construct one or more advertisements for each of the one or more keyword clusters.

43. The system of claim 29, wherein each of the one or more intent topics of the intent map relates to one or more intent-topic categories.

44. The system of claim 43, wherein the one or more intent-topic categories comprise one or more of product categories, products, general product descriptions, specific product descriptions, calls to action, or call-to-action descriptions.

45. The system of claim 29, wherein the one or more intent topics form one or more hierarchies.

46. The system of claim 45, wherein each of the one or more hierarchies comprises:

a set of intent topics, comprising at least one of the one or more intent topics; and

a plurality of levels, each comprising at least one intent topic from the set of intent topics.

47. The system of claim 46, wherein:

each of the one or more intent topics belongs to one of a plurality of intent-topic categories; and

for each of the one or more hierarchies, each intent topic from the set of intent topics belongs to a common intent-topic category.

48. The system of claim 29, wherein there are one or more topic relationships among the one or more intent topics and one or more intent relationships among the one or more intents of the one or more intent topics.

49. The system of claim 48, wherein one of the one or more topic relationships between a first intent topic and a second intent topic indicates that a first intent belonging to the first intent topic and a second intent belonging to the second intent topic are either eligible or not eligible to appear together in at least one of the plurality of keywords.

50. The system of claim 48, wherein one of the one or more intent relationships between a first intent belonging to a first intent topic and a second intent belonging to a second intent topic indicates that the first intent and the second intent are eligible to appear together in at least one of the plurality of keywords.

51. The system of claim 48, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a synonym of the second intent.

52. The system of claim 48, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a plural form of the second intent.

53. The system of claim 48, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a misspelling of the second intent.

54. The system of claim 48, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent and the second intent are eligible to be substitutes for each other in at least one of the plurality of keywords.

55. The system of claim 29, wherein the plurality of products belongs to a same business or industry.

56. The system of claim 29, where a product is a physical product, a software product, or a service.

57. One or more computer-readable non-transitory storage media embodying software operable when executed by one or more computer systems to:

construct an intent map for a plurality of products, wherein;

the intent map comprises one or more intent topics, and

each of the one or more intent topics comprises one or more intents; and

derive a plurality of keywords from the intent map based on one or more keyword templates.

58. The media of claim 57, wherein the software is further operable when executed by the one or more computer systems to construct the one or more keyword templates.

59. The media of claim 58, wherein at least one of the one or more keyword templates is constructed based on one or more rules.

60. The media of claim 59, wherein the one or more rules are determined based on the one or more intent topics.

61. The media of claim 58, wherein:

the one or more intent topics form a hierarchy; and

at least one of the one or more keyword templates is constructed based on the hierarchy.

62. The media of claim 58, wherein at least one of the one or more keyword templates is constructed based on a collection of known keywords, comprising:

analyze the collection of known keywords;

select, from the collection of known keywords, one or more known keywords that are applicable to the intent map; and

construct the at least one of the one or more keyword templates based on the one or more known keywords.

63. The media of claim 62, wherein selecting, from the collection of known keywords, the one or more known keywords that are applicable to the intent map comprises:

select, from the collection of known keywords, one or more specific known keywords that are related to the plurality of products;

analyze historical performance information of the one or more specific known keywords that are related to the plurality of products; and

select, from the one or more specific known keywords that are related to the plurality of products, the one or more known keywords that have relatively higher performance with respect to one or more predetermined metrics.

64. The media of claim 62, wherein constructing the one or more keyword templates based on the one or more known keywords comprises:

for each of the one or more known keywords,

divide the known keyword into one or more segments; and

for each of at least one of the one or more segments,

identify an intent from the intent map that aligns with the segment; and

replace the segment with an intent topic from the intent map to which the intent belongs.

65. The media of claim 57, wherein at least one of the one or more keyword templates comprises at least one intent topic from the intent map.

66. The media of claim 65, wherein deriving the plurality of keywords from the intent map based on the one or more keyword templates comprises:

derive one or more of the plurality of keywords based on each of the one or more keyword templates;

wherein;

the one or more intent topics form a hierarchy; and

deriving one of the plurality of keywords based on one of the one or more keyword templates comprises replace each of the at least one intent topic contained in the one keyword template with an intent from the intent topic or from an intent topic that is an ancestor of the intent topic in the hierarchy.

67. The media of claim 57, wherein the software is further operable when executed by the one or more computer systems to filter the plurality of keywords, comprising:

estimate a marketing or advertising volume for the plurality of keywords; and

select, from the plurality of keywords, one or more keywords that are estimated to generate a relatively higher marketing or advertising volume.

68. The media of claim 57, wherein the software is further operable when executed by the one or more computer systems to cluster the plurality of keywords into one or more keyword clusters.

69. The media of claim 68, wherein clustering the plurality of keywords into the one or more keyword clusters comprises:

specify a set of intent topics along which to cluster, wherein the set of intent topics comprises at least one of the one or more intent topics; and

group the plurality of keywords based on the set of intent topics, comprising;

group all keywords that, for each intent topic in the set of intent topics commonly share a same intent from that intent topic, into a keyword cluster.

70. The media of claim 68, wherein the software is further operable when executed by the one or more computer systems to construct one or more advertisements for each of the one or more keyword clusters.

71. The media of claim 57, wherein each of the one or more intent topics of the intent map relates to one or more intent-topic categories.

72. The media of claim 71, wherein the one or more intent-topic categories comprise one or more of product categories, products, general product descriptions, specific product descriptions, calls to action, or call-to-action descriptions.

73. The media of claim 57, wherein the one or more intent topics form one or more hierarchies.

74. The media of claim 73, wherein each of the one or more hierarchies comprises:

a set of intent topics, comprising at least one of the one or more intent topics; and

a plurality of levels, each comprising at least one intent topic from the set of intent topics.

75. The media of claim 74, wherein:

each of the one or more intent topics belongs to one of a plurality of intent-topic categories; and

for each of the one or more hierarchies, each intent topic from the set of intent topics belongs to a common intent-topic category.

76. The media of claim 57, wherein there are one or more topic relationships among the one or more intent topics and one or more intent relationships among the one or more intents of the one or more intent topics.

77. The media of claim 76, wherein one of the one or more topic relationships between a first intent topic and a second intent topic indicates that a first intent belonging to the first intent topic and a second intent belonging to the second intent topic are either eligible or not eligible to appear together in at least one of the plurality of keywords.

78. The media of claim 76, wherein one of the one or more intent relationships between a first intent belonging to a first intent topic and a second intent belonging to a second intent topic indicates that the first intent and the second intent are eligible to appear together in at least one of the plurality of keywords.

79. The media of claim 76, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a synonym of the second intent.

80. The media of claim 76, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a plural form of the second intent.

81. The media of claim 76, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent is a misspelling of the second intent.

82. The media of claim 76, wherein one of the one or more intent relationships between a first intent and a second intent indicates that the first intent and the second intent are eligible to be substitutes for each other in at least one of the plurality of keywords.

83. The media of claim 57, wherein the plurality of products belongs to a same business or industry.

84. The media of claim 57, where a product is a physical product, a software product, or a service.

85. A system comprising:

means for constructing an intent map for a plurality of products, wherein;

the intent map comprises one or more intent topics, and

each of the one or more intent topics comprises one or more intents; and

means for deriving a plurality of keywords from the intent map based on one or more keyword templates.